INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iquette

-0.77

astically

-0.74

eworthy

-0.73

icho

-0.68

 Flavoring

-0.67

 Cornwall

-0.66

 Volcano

-0.66

pedia

-0.65

 Jarrett

-0.64

istan

-0.64

POSITIVE LOGITS

've

1.01

're

0.89

'll

0.83

 think

0.82

'd

0.81

'm

0.79

 dunno

0.79

 dont

0.76

 remember

0.75

soDeliveryDate

0.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.